Yunzhe Tao
Papers
3
Total Citations
121
H-Index
3
About
Yunzhe Tao is a researcher working at the intersection of reinforcement learning, autonomous systems, and sim-to-real transfer — areas that are increasingly central to the future of intelligent robotics and self-driving technology. Tao is best known as a key contributor to the **AWS DeepRacer** project, an innovative 1/18th-scale autonomous racing platform designed to democratize experimentation with reinforcement learning. The DeepRacer platform enables end-to-end RL research using only a monocular camera, providing researchers and students alike with a tangible, accessible testbed for tackling the notoriously difficult sim-to-real transfer problem. The 2020 paper describing the platform has accumulated 82 citations, reflecting its broad adoption and influence in both academic and educational communities. Tao's work on zero-shot reinforcement learning further advances this agenda, exploring deep attention convolutional neural networks as a means of bridging the reality gap without requiring real-world retraining. Collectively, Tao's contributions have helped lower the barrier to entry for RL research, fostered a global community of autonomous racing enthusiasts, and pushed forward foundational understanding of how simulated training can translate meaningfully into real-world intelligent control systems.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3